A Hierarchical Attention-Based Method for Sleep Staging Using Movement and Cardiopulmonary Signals.

Sleep monitoring typically requires the uncomfortable and expensive polysomnography (PSG) test to determine the sleep stages. Body movement and cardiopulmonary signals provide an alternative way to perform sleep staging. In recent years, long-short term memory (LSTM) networks and convolutional neural networks (CNN) have dominated automatic sleep staging due to their better learning ability than machine learning classifiers. However, LSTM may lose information when dealing with long sequences, while CNN is not good at sequence modeling. As an improvement, we develop a hierarchical attention-based deep learning method for sleep staging using body movement, electrocardiogram (ECG), and abdominal breathing signals. We apply the multi-head self-attention to model the global context of feature sequences and coupled it with CNN to achieve a hierarchical self-attention weight assignment. We evaluate the performance of the method using two public datasets. Our method outperforms other baselines in the three sleep stages, achieving an accuracy of 84.3%, an F1 score of 0.8038, and a Cohen's Kappa coefficient of 0.7036. The result demonstrates the effectiveness of the hierarchical self-attention mechanism when processing feature sequences in the sleep stage classification problem. This paper provides new possibilities for long-term sleep monitoring using movement and cardiopulmonary signals obtained from non-invasive devices. The code can be found at: https://github.com/scutrd/attention-sleep-staging.

Disease suppression on greenhouse tomatoes using plant waste compost.

This study investigated the disease suppression abilities of a compost amendment that was added to the conventional growing medium, yellow cedar sawdust, used in most British Columbia vegetable greenhouses. The compost amendment was produced in a controlled, in-vessel process primarily from greenhouse crop waste materials. The pathogen and cultivar under study were Fusarium oxysporum f. sp. radicis-lycopersici (FORL) on Dombito (FORL-susceptible) beefsteak greenhouse tomatoes. Significant reduction of Fusarium crown and root rot was also realized in tomato seedlings by applying compost amendment from several different batches, as a seed cover or plug substitute. In a greenhouse trial, disease suppression using a mixture of 2:1 sawdust to amendment by volume was shown to be most effective. As a result, the tomato yield over a nine-month growing season was improved by 74% where the medium was deliberately infested with FORL.

A comparison of swine wastewater treatment using real-time and fixed-time two-stage sequencing batch reactors.

This study compared the swine wastewater treatment of two identical lab-scale two-stage sequencing batch reactors (TSSBR) under similar conditions except that one was operated on a fixed-time mode and the other on a real-time mode. While both TSSBR systems performed very well, the real-time TSSBR performed far better then the fixed-time TSSBR, in every aspect of carbon, nitrogen, and phosphorous removal. The removals of COD, TOC, were at 97% and for BOD5 even at 99.7%. In terms of NH4-N and TKN removals, the real-time TSSBR achieved removal of over 98%. For phosphorus removals (Ortho-P and total P) the results from the real-time TSSBR was quite remarkable at 97.7%.

Benefits of sustainable waste management in the vegetable greenhouse industry.

This study investigated the benefits of an on-site sustainable solid waste treatment and utilization system for the greenhouse industry. The composts made from greenhouse wastes were tested and found to contain high nutrient values and good physical properties, and could be used as high quality growing media. The finished composts were tested in a greenhouse against the conventional growth media (sawdust) and resulted in a 10% yield increase by using the compost. An economic analysis was conducted to show the economic benefits of on-site composting for a greenhouse operation. Based on a four-hectare tomato or pepper greenhouse, and amortizing the capital equipment over five years, the net annual cost of composting represents a savings of dollars 8,000 annually.